Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    curly braces used in programming and code structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Picchu
    -0.78
     Beller
    -0.77
     Mahi
    -0.73
     Suri
    -0.73
     BoxDecoration
    -0.73
    FieldDescriptor
    -0.72
     Superhosts
    -0.71
     umani
    -0.71
    ten
    -0.69
     miy
    -0.68
    POSITIVE LOGITS
    oporosis
    0.73
    lapsingToolbar
    0.73
    ".
    0.72
    nmgp
    0.71
    wisata
    0.70
    ”,
    0.69
    "},
    0.68
    ểm
    0.68
    AFFIRMED
    0.66
    oldValue
    0.66
    Act Density 0.036%

    No Known Activations